© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 5-ATT-KK
    11. 44005
    Prev
    Next
    INDEX
    Explanations

    references to health-related studies and assessments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    Data Type
    float32
    Hook Name
    blocks.5.attn.hook_z
    Hook Layer
    5
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.05
    1:0.02
    2:0.08
    3:0.13
    4:0.06
    5:0.05
    6:0.03
    7:0.05
    8:0.04
    9:0.10
    10:0.19
    11:0.15
    Negative Logits
     Says
    -1.17
     destro
    -1.15
    bender
    -1.14
    OPA
    -1.12
     lately
    -1.11
     Gadget
    -1.11
    kos
    -1.09
     Gets
    -1.09
    uably
    -1.05
    asonic
    -1.04
    POSITIVE LOGITS
     chronological
    1.28
     ∼
    1.19
     receipt
    1.16
    details
    1.13
    RESULTS
    1.12
    Results
    1.12
    �醒
    1.11
    Particip
    1.11
     schedule
    1.11
     heterogeneity
    1.10
    Activations Density 0.058%

    No Known Activations